Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the participation or inclusion in processes or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĨداÙĨ
    -0.16
    avana
    -0.15
    ihn
    -0.15
    姿
    -0.15
    Ìģc
    -0.13
     Panic
    -0.13
    ha
    -0.13
    ÏĦÎŃ
    -0.13
    -FIRST
    -0.13
    ç¯ĩ
    -0.13
    POSITIVE LOGITS
    rok
    0.16
    ør
    0.15
    borg
    0.15
    ÙĪÙĦÙĩ
    0.14
    ailles
    0.14
    ajes
    0.14
    ÐĴаж
    0.14
    rome
    0.14
     legality
    0.14
    orig
    0.14
    Act Density 0.010%

    No Known Activations